© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15295
    Prev
    Next
    INDEX
    Explanations

    turbo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADELPHIA
    -0.57
    ÍS
    -0.54
    ú
    -0.50
    unta
    -0.49
    levé
    -0.49
    tieth
    -0.47
    mstyle
    -0.47
    Starring
    -0.47
    pota
    -0.46
    nuff
    -0.46
    POSITIVE LOGITS
     متعلقه
    0.69
     oprot
    0.66
    InjectAttribute
    0.63
    RefNanny
    0.62
    cetin
    0.59
     extranjera
    0.54
    acjach
    0.52
    obiety
    0.51
     worshipped
    0.51
    UnknownFields
    0.51
    Activations Density 0.026%

    No Known Activations